// SCAN REPORT

Local DeepWiki MCP Server

65 tools. 8 can modify or destroy data without limits.

1 destructive tool with no built-in limits. Policy required.

Last updated: 29 Jun 2026

8 can modify or destroy data

57 read-only

65 tools total

Community server · catalogue entry verified 29/06/2026

How to control Local DeepWiki MCP Server ↓

TOOL MAP

What Local DeepWiki MCP Server exposes to your agents

Read (57) Write / Execute (7) Destructive / Financial (1)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Local DeepWiki MCP Server tools

Destructive · High cancel_research Cancel an active deep research session and save its checkpoint. Execute · Medium run_workflow Run a pre-built multi-step workflow. Available presets: Execute · Medium serve_wiki Start the interactive wiki web server for a .deepwiki directory. Execute · Medium stop_wiki_server Stop a previously started wiki web server. Gracefully terminates

8 of Local DeepWiki MCP Server's 65 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Local DeepWiki MCP Server

PolicyLayer is an MCP gateway — it sits between your AI agents and Local DeepWiki MCP Server, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations

{
  "cancel_research": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

{
  "export_wiki_html": {
    "limits": [
      {
        "counter": "export_wiki_html_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "analyze_architecture": {
    "limits": [
      {
        "counter": "analyze_architecture_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Local DeepWiki MCP Server — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON LOCAL DEEPWIKI →

Instant setup, no code required.

FULL CATALOGUE

All 65 Local DeepWiki MCP Server tools

DESTRUCTIVE 1 tools

Destructive cancel_research Cancel an active deep research session and save its checkpoint.

EXECUTE 3 tools

Execute run_workflow Run a pre-built multi-step workflow. Available presets: Execute serve_wiki Start the interactive wiki web server for a .deepwiki directory. Execute stop_wiki_server Stop a previously started wiki web server. Gracefully terminates

WRITE 4 tools

Write export_wiki_html Export wiki documentation to static HTML files. Creates a Write export_wiki_pdf Export wiki documentation to PDF format. Creates a printable PDF Write generate_codemap Generate a Windsurf-style codemap: a focused execution-flow map with Write resume_research Resume a previously interrupted deep research session from its

READ 57 tools

Read analyze_architecture Comprehensive architecture analysis in a single call. Runs health Read analyze_diff Analyze git diff between two refs. Supports two modes:\n Read ask_about_diff Ask questions about recent code changes using RAG. Combines git Read ask_question Ask a question about an indexed repository using RAG. Returns an Read batch_explain_entities Explain multiple code entities in a single call. Loads the search Read compare_architecture Compare architecture health between two git refs. Shows which Read deep_research Perform deep research on a codebase question using multi-step reasoning. Read detect_bugs Scan a repository for potential bugs using AST pattern matching. Read detect_secrets Scan a repository for hardcoded credentials and secrets (API keys, Read detect_stale_docs Find wiki pages that may be outdated because their source files Read explain_entity Get a comprehensive explanation of a function, class, or method Read find_tools Search for tools by capability description. Returns ranked matches Read fuzzy_search Fuzzy name matching for functions, classes, and methods using Read get_api_docs Get API documentation with function signatures, parameters, return Read get_architecture_health Comprehensive architecture health check. Runs complexity hotspot Read get_architecture_summary Deprecated: use get_architecture_health with detail_level= Read get_architecture_trends View architecture health score trends over time. Returns historical Read get_call_graph Get function call graphs showing which functions call which. Can Read get_changelog Extract recent git commit history as a formatted changelog. Read get_churn_metrics Analyze file change frequency from git history. Shows which files Read get_co_change Find files that frequently change together in the same commits. Read get_cohesion_metrics Analyze class and module cohesion. Reports LCOM4 (Lack of Read get_complexity_metrics Analyze code complexity for a source file using tree-sitter AST Read get_coupling_metrics Compute Robert C. Martin package-level coupling metrics per module: Read get_coverage Get documentation coverage report for an indexed repository. Read get_cross_module_dependencies Build an inter-module import graph for a Python repository. Read get_design_smells Detect common design smells using heuristic AST-based thresholds: Read get_diagrams Generate Mermaid diagrams for an indexed repository. Supports class Read get_duplication_metrics Detect code duplication using two methods: exact clones (Type 1, Read get_file_context Get rich context for a source file: imports, callers (who uses Read get_glossary Get a searchable glossary of all code entities (classes, functions, Read get_guided_tour Generate a guided tour of a codebase organized by topic. Returns an Read get_hotspots Rank functions across an entire repository by a chosen complexity Read get_index_status Get index statistics for a repository without re-indexing. Read get_inheritance Get class inheritance hierarchy trees for an indexed repository. Read get_layer_dependencies Analyze architectural layer dependencies in a Python codebase. Read get_maintainability_metrics Compute Maintainability Index (MI) per function across a Python Read get_module_health Deep health analysis of a single module. Shows complexity Read get_onboarding_guide Generate a developer onboarding guide for a codebase. Returns a Read get_operation_progress Get progress for active long-running operations. Supports Read get_project_manifest Get parsed project metadata from package manifest files Read get_recommendations Generate prioritized refactoring recommendations from architecture Read get_status Get repository index status and/or wiki health dashboard.\n Read get_test_examples Find usage examples for a function or class by searching test Read get_testability_metrics Analyze testability metrics for a Python repository. Reports Read get_wiki_stats Get a wiki health dashboard with index stats, page counts, Read impact_analysis Analyze the blast radius of changes to a file or entity. Combines Read index_repository Index a repository and generate wiki documentation. This parses all Read list_indexed_repos Discover all indexed repositories under a given directory. Read list_research_checkpoints List all research checkpoints for a repository. Shows incomplete Read query_codebase Smart query that combines ask_question with automatic escalation Read read_wiki_page Read a specific wiki page content. Read read_wiki_structure Get the table of contents and structure of a generated wiki. Read search_code Semantic search across the indexed codebase with optional fuzzy Read search_wiki Full-text search across wiki pages and code entities. Searches Read suggest_codemap_topics Suggest interesting codemap topics for a repository based on call graph hubs, Read suggest_next_actions Suggest which tools to use next based on tools already used.

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about Local DeepWiki MCP Server

Can an AI agent delete data through the Local DeepWiki MCP Server MCP server? +

Yes. The Local DeepWiki MCP Server server exposes 1 destructive tools including cancel_research. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Local DeepWiki MCP Server? +

The Local DeepWiki MCP Server server has 4 write tools including export_wiki_html, export_wiki_pdf, generate_codemap. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Local DeepWiki MCP Server.

How many tools does the Local DeepWiki MCP Server MCP server expose? +

65 tools across 4 categories: Destructive, Execute, Read, Write. 57 are read-only. 8 can modify, create, or delete data.

How do I enforce a policy on Local DeepWiki MCP Server? +

Register the Local DeepWiki MCP Server MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Local DeepWiki MCP Server tool call.

Deterministic rules across all 65 Local DeepWiki MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON LOCAL DEEPWIKI →

Instant setup, no code required.

65 Local DeepWiki MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.